论文标题

解开动作序列:发现相关样品

Disentangling Action Sequences: Discovering Correlated Samples

论文作者

Wu, Jiantao, Wang, Lin

论文摘要

由于人类与人类的理解和推理的相似之处,解开是代表性的非常可取的特性。这可以提高可解释性,实现下游任务的执行,并实现可控的生成模型。但是,该领域受到抽象概念和不完整理论的挑战,以支持无监督的分解学习。我们演示了数据本身,例如图像的方向,在分离中起着至关重要的作用,而不是因素,而解散表示的表示潜在变量将潜在变量与动作序列保持一致。我们进一步介绍了解开动作序列的概念,该序列有助于描述现有的解开方法的行为。这个过程的一个类比是发现事物之间的共同点并分类它们。此外,我们分析了数据上的电感偏差,并发现潜在信息阈值与动作的重要性相关。对于受监督和无监督的设置,我们分别引入了两种测量阈值的方法。我们进一步提出了一个新颖的框架,即分数自动编码器(FVAE),以逐步解散具有不同意义的动作序列。 DSPRITES和3D椅子的实验结果表明,FVAE提高了分离的稳定性。

Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable generative models. However, this domain is challenged by the abstract notion and incomplete theories to support unsupervised disentanglement learning. We demonstrate the data itself, such as the orientation of images, plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with the action sequences. We further introduce the concept of disentangling action sequences which facilitates the description of the behaviours of the existing disentangling approaches. An analogy for this process is to discover the commonality between the things and categorizing them. Furthermore, we analyze the inductive biases on the data and find that the latent information thresholds are correlated with the significance of the actions. For the supervised and unsupervised settings, we respectively introduce two methods to measure the thresholds. We further propose a novel framework, fractional variational autoencoder (FVAE), to disentangle the action sequences with different significance step-by-step. Experimental results on dSprites and 3D Chairs show that FVAE improves the stability of disentanglement.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源